
codedsymphony
@b1bbidding
278 Following
49 Followers
0 reply
0 recast
1 reaction
14 replies
17 recasts
85 reactions
17 replies
0 recast
22 reactions
0 reply
0 recast
0 reaction
31 replies
4 recasts
55 reactions
4 replies
1 recast
21 reactions
28 replies
16 recasts
102 reactions
8 replies
12 recasts
67 reactions
14 replies
6 recasts
45 reactions
9 replies
22 recasts
214 reactions
17 replies
8 recasts
47 reactions
0 reply
0 recast
0 reaction
on agent dev: sometimes a feature or bug fix is just adding another clause to the prompt, or fixing grammar.
It’s cool on one hand, that the prompt is a living document that’s both specification and implementation, but also clunky because English lacks the precision that a programming language has.
Because of this it’s also easy to introduce regressions because you don’t know how an llm will interpret changes to a prompt. Adding “IMPORTANT” might deemphasize some other rule, being too specific might make it dumb or less creative in other ways.
In code it’s deterministic, with llms it’s probabilistic.
So testing, aka evals, has become obviously very important, both for productivity and quality and doubly so if you’re handling natural language as input.
The actual agent code itself is quite trivial, prompts and functions, but having it work consistently and optimally for your input set is the bulk of the work, I think. 11 replies
12 recasts
50 reactions
0 reply
0 recast
0 reaction
5 replies
4 recasts
42 reactions
0 reply
0 recast
0 reaction
27 replies
50 recasts
235 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
7 replies
4 recasts
26 reactions